- Researchers are currently developing deep learning AI to count sea cows in images taken with cameras.
- This model was trained to identify sea cows in shallow waters, this is expected to help plan conservation actions.
- Currently, models are still imperfect, and it is sometimes difficult to differentiate between adult calves and calves, or between males and females.
- The team said it plans to continue training the model in the next few months, while working with biologists for input.
Artificial intelligence (AI) technology is now starting to be used by researchers to understand wild life. Researchers assess that the use of AI will provide understanding and calculate animal populations.
In a model developed by researchers from Florida Atlantic University (FAU), they used an AI-based method to count sea cows or manatees (Trichechus spp), a species of marine mammal, from images collected via video. The results of the study, published in the journal Scientific Reports, saw researchers using low-resolution images to estimate the population of this species in shallow waters.
“This model will help understand sea cow demographics in real-time,” study lead author Xingquan Zhu, a professor in FAU's Department of Electrical Engineering and Computer Science.
“This will help plan conservation actions, prevent habitat loss, and design rules for boaters and divers.”
So far, sea cows have long been tracked with the help of GPS devices attached to their tails. However, the weakness is that the marine environment causes the device to quickly become damaged. The use of physical tags also limits the number of animals that can be monitored at once.
This data gap is what prompted Zhu and his team to adopt artificial intelligence to estimate sea cow populations in an affordable and real-time manner.
So how do you implement AI?
The first step is to collect as many video images as possible to train an AI model collected from various videos from various conservation areas.
“The images come from different times and seasons, and from a variety of different shooting angles.”
To start, the team collected thousands of videos, and from there they selected nearly 700 different frames to train the AI model. They also ensured a good mix of images showing groups of sea cows in varying numbers.
“In some areas, you only see one or two sea cows, but in some different locations you can find almost 40 or 50,” Zhu said.
In this model, researchers carry out the process continuously, until the entire image can be analyzed.
“The goal is to combine all these types of images and train a model to distinguish each individual from a variety of image pixels.”
In this training process, the AI sometimes mistook large fish for sea cows, or confused them with images of inanimate objects.
“If you put a toy that resembles a sea cow into water, the model will recognize it as a sea cow. "Similarly [can be confused] between individual sea cows and calves, as well as males and females," said Zhu.
In the future, Zhu said he hopes to work with biologists to refine the model and get their input on their results.
How do you count manatees? Ideally, standing by a river while playing with the aquatic mammals. However, in a world where manatee populations face increasing threats, a faster and more accurate method is imperative.
Enter artificial intelligence.
A model developed by scientists at Florida Atlantic University uses a deep-learning-based method to count manatees in images captured by cameras. A study published in the journal Scientific Reports describes how the model can use even low-quality images to estimate manatee populations in shallow waters.
“Eventually, we think this model will be very helpful to understand manatee demographics in real time,” study lead author Xingquan Zhu, a professor at FAU’s Department of Electrical Engineering and Computer Science, in a video interview. “How many are there? What are their habitats? Where do they go for food?”
Answering these questions is helpful to plan conservation actions, prevent habitat loss, and design rules for boaters and divers.
Manatees (Trichechus spp.) have long been tracked with the help of GPS devices attached to their tails. However, the harsh marine environments they often inhabit lead to the tags breaking down quickly. The use of physical tags also imposes a restriction on the number of animals that can be monitored in one go. “Plus it’s also quite labor-intensive,” Zhu said.
The first step entailed gathering images with which to train the model. Initially, the team thought of using images from the internet. However, realizing that these wouldn’t be nearly enough, they turned to another source.
“We realized there are quite a lot of videos from the U.S. state parks, and those videos gave us a lot of information,” Zhu said. “They captured manatees on different days, and from different angles in the same spot. They also showed us manatees in different seasons.”
Capturing images from videos was, in itself, a task. To start with, the team had access to thousands of videos, from which they picked close to 700 different frames to train the model. They also had to ensure a good mix of images that showed manatee groups of varying numbers. “In some of the areas, you see only one or two manatees, and in some of them you see close to even 40 or 50,” Zhu said. “We wanted to mix all these types of images.”
With the data in place, the team worked on labeling the manatees in the images. “Labeling essentially means to teach the model, ‘Hey, this is a manatee. This is what it looks like,’” Zhu said.
The model, however, doesn’t directly recognize or understand shapes per se. When a user inputs an image into the model, it takes small patches of pixels from the image and checks it against the labels it was trained on. The model’s algorithm then “basically says ‘Yes, you are correct. No, you are wrong,’” Zhu said. “This process goes on continuously back and forth, back and forth, until the whole image is analyzed.” Once done, the model outputs an estimate of the number of manatees in the image.
However, it’s not always smooth sailing.
Often, the model confuses large fish for manatees. It can also be bamboozled by inanimate objects. “If you put a toy that resembles a manatee in water, the model will recognize it as a manatee,” Zhu said.
Additionally, the model can’t yet distinguish between adults and calves, or between males and females — distinctions that often play a vital role for conservation as well as research purposes.
Zhu said he hopes to work with biologists to improve the model. “The reason we haven’t done that yet is because we were trying to use the computation to see if we got results,” he said. “Now that the results are promising, the next step is to work with biologists and get their feedback.”
He said the team also plans to keep training the model so that it gets better and more efficient. “With deep learning, you can just keep training it,” he said. “There’s normally no end.”